Search

Text simplification reduces the complexity of text while preserving essential information, thus making it more accessible to a broad range of readers, including individuals with cognitive disorders, non-native speakers, children, and the general public. In this paper, we present experiments on text simplification for the Lithuanian language, aiming to simplify administrative texts to a Plain Language level. We fine-tuned mT5 and mBART models for this task and evaluated the effectiveness of ChatGPT as well. We assessed simplification results via both quantitative metrics and qualitative evaluation. Our findings indicated that mBART performed the best as it achieved the best scores across all evaluation metrics. The qualitative analysis further supported these findings. ChatGPT experiments showed that it responded quite well to a short and simple prompt to simplify the given text; however, it ignored most of the rules given in a more elaborate prompt. Finally, our analysis revealed that BERTScore and ROUGE aligned moderately well with human evaluations, while BLEU and readability scores indicated lower or even negative correlations [ABSTRACT FROM AUTHOR]

Imbalanced datasets are one of the main issues encountered by artificial intelligence researchers, as machine learning (ML) algorithms can become biased toward the majority class and perform insufficiently on the minority classes. Financial distress (FD) is one of the numerous real-world applications of ML, struggling with this issue. Furthermore, the topic of financial distress holds considerable interest for both academics and practitioners due to the non-determined indicators of condition states. This research focuses on the involvement of balancing techniques according to different FD condition states. Moreover, this research was expanded by implementing ML models and dimensionality reduction techniques. During the course of this study, a Combined FD was constructed using five distinct conditions, ten distinct class balancing techniques, five distinct dimensionality reduction techniques, two features selection strategies, eleven machine learning models, and twelve weighted majority algorithms (WMAs). Results revealed that the highest area under the receiver operating characteristic (ROC) curve (AUC) score was achieved when using the extreme gradient boosting machine (XGBoost) feature selection technique, the experimental max number strategy, the undersampling methods, and the WMA 3.1 weighted majority algorithm (i.e., with categorical boosting (CatBoost), XGBoost, and random forest (RF) having equal voting weights). Moreover, this research has introduced a novel approach for setting the condition states of financial distress, including perspectives from debt and change in employment. These outcomes have been achieved utilizing authentic enterprise data from small and medium Lithuanian enterprises. [ABSTRACT FROM AUTHOR]

Financial distress identification remains an essential topic in the scientific literature due to its importance for society and the economy. The advancements in information technology and the escalating volume of stored data have led to the emergence of financial distress that transcends the realm of financial statements and its' indicators (ratios). The feature space could be expanded by incorporating new perspectives on feature data categories such as macroeconomics, sectors, social, board, management, judicial incident, etc. However, the increased dimensionality results in sparse data and overfitted models. This study proposes a new approach for efficient financial distress classification assessment by combining dimensionality reduction and machine learning techniques. The proposed framework aims to identify a subset of features leading to the minimization of the loss function describing the financial distress in an enterprise. During the study, 15 dimensionality reduction techniques with different numbers of features and 17 machine-learning models were compared. Overall, 1,432 experiments were performed using Lithuanian enterprise data covering the period from 2015 to 2022. Results revealed that the artificial neural network (ANN) model with 30 ranked features identified using the Random Forest mean decreasing Gini (RF_MDG) feature selection technique provided the highest AUC score. Moreover, this study has introduced a novel approach for feature extraction, which could improve financial distress classification models. [ABSTRACT FROM AUTHOR]

Copyright of Vilnius University Open Series is the property of Vilnius University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Forests established through afforestation are one of the most precious natural resources, especially in harsh and desert-biased conditions. Trees are often exposed to various threats that need to be addressed. Some of the threats are igniting fires, illegal lumberjacking, hunting, using, and crossing prohibited areas, etc. This article delves into the combination of advanced technologies, such as radars, thermal imaging, remote sensing, artificial intelligence, and biomass monitoring systems, in the field of forestry and natural resource security. By examining the parametric assurance technologies described in this paper, the potentials of real-time monitoring, early detection of threats, and rapid response capabilities are examined, which significantly improves the efficiency of forest protection efforts. This article deals with the presentation of advanced algorithms that include radar, thermal cameras, and artificial intelligence, which enable the automatic identification and classification of potential threats with a false alarm rate (FAR) as low as possible. The article presents a systemic solution that optimizes the answer for a parametric security system that is required to work in a complex environment with multiple triggers that can cause false alarms. In addition to this, a presented system is required to be easy to assemble and have the ability to integrate into natural areas and serve as a vulnerable aid in nature as much as possible. In conclusion, this study highlights the transformative potential of security applications in improving forest and natural reserve security while taking into account the complexity of the environment. [ABSTRACT FROM AUTHOR]

According to the Transport Innovation Association estimations, on average, a single lorry driver carries about 50 sheets of paper consisting of only 15 CMR documents. In Lithuania alone, there are about 50,000 active trucks each month, resulting in about 192 tonnes of wasted paper annually. The manual entry of document data into enterprise resource planning (ERP) systems not only is time-consuming but inefficient and could consist of errors. To address these issues, a framework for the digitisation of logistic documents, such as invoices, receipts and CMRs, is proposed that uses object detection, optical character recognition (OCR) and a semi-supervised finetuning pipeline. This study focuses on both the experimentation and implementation phases of research. During the experimentation phase, multiple object detection models like SSD MobileNet, SSD ResNet-50, Faster-RCNN, EfficientDet-D4, and CenterNet HourGlass104 were evaluated. OCR models like Tesseract, EasyOCR, KerasOCR, Kraken, Doctr, and Google OCR were tested. Extensive evaluations showed that using the combination of Faster-RCNN and Google OCR works the best for document digitisation. The object detection model was trained using approximately 1000 images that were equally distributed among three classes of documents. The Faster-RCNN model achieved an average precision (AP) of 0.95 at an Intersection over the Union (IoU) threshold of 0.5, 0.84 AP at an IoU of 0.75, and 0.71 AP IoU ranging from 0.5 to 0.95, with an average recall (AR) of 0.75, within the same range. OCRs performances were manually assessed due to the lack of annotations, with Google OCR proving the best results in the presence of minor inaccuracies in bounding box placement or noise within the bounding box. To further increase the accuracy of the object detection model, a semi-automated labelling process was introduced, where a trained Faster-RCNN model is used to generate initial bounding boxes and class labels on unseen data, which later are manually adjusted for further finetuning of a pre-trained Faster-RCNN model. The proposed system is an improvement in automating logistics document digitisation, reducing dependence on manual labour and an overall increase of efficiency in the transportation industry. [ABSTRACT FROM AUTHOR]

The precise identification of enterprise activity codes stands as a crucial task enabling the rapid and effective establishment or renewal of databases encompassing both public and private companies, which in return helps to make an informative decision about countries' economic tendencies. The research involves combining multi-source datasets, data cleaning, explanatory data analysis, retrieval of embeddings, feature selection, the optimal number of clusters identification, data clustering, and post-clustering analysis. Gathered insights allow for informative decisions about taxes, needed state aid and competition analysis. In both the Republic of Lithuania and the European Union, the enterprise classification system operates under the Nomenclature of Economic Activities (NACE), which employs a six-digit framework. For instance, code 461900 indicates that the business conducts the sales of various goods that involve agents. The initial two digits represent overarching enterprise classifications, in this case, retail trade, while the final four digits delineate specific categorisations within the country's industries. This study aims to apply clustering methods to help in the identification of the economic activities of enterprises using descriptions that could be found in the "Company Description" section of the rekvizitai.lt website. The dataset consists of 28350 business descriptions. Two main themes were observed in the data: (1) the average description lengths are 14, excluding stop-words; (2) the most common activities in the Lithuania economic sector are wholesale, retail, agriculture, and service industry. In this study, 3 embedding methods (BERT, LaBSE and Word2Vec), 4 feature selection methods (PCA, UMAP, SVD, and autoencoders) and 8 clustering methods (K-means, GMM, agglomerative, mean shift, OPTICS, BIRCH, HDBSCAN, DEC) were used for experimentations with 195 models trained in total. Three main metrics, silhouette score, Davies Bouldin score, and Calinski-Harabasz Index, are evaluated across all clustering algorithms, with adjusted Rand Index and mutual information evaluated for hard-clustering methods. The initial experiments showed that LaBSE and Word2Vec are the most prominent methods for embedding retrieval, while PCA and UMAP are most suitable for dimensionality reduction. The elbow approach was employed in additional experiments to determine the ideal number of clusters. Although these experiments demonstrated that data may be grouped into fewer clusters, the outcomes did not indicate a statistically significant improvement, and adhering to the original NACE space facilitates a more accurate assessment of the current economic landscape situation. Clustering results from K-means, agglomerative, and mean shift methods showed good intra-clustering and slightly above average inter-clustering results. This research demonstrates that enterprise activity sectors can be categorised using Lithuanian descriptions and the K-means, agglomerative, or mean shift clustering algorithms. Future research will focus on all three algorithms hyperparameter optimisation to improve inter-clustering and intra-clustering results. [ABSTRACT FROM AUTHOR]

Monitoring social and traditional media requires handling vast amounts of unstructured data, which can be challenging to manage and analyse effectively In such scenarios, techniques that can extract only key information, reducing the data volume and organising it into structured formats, prove to be highly beneficial. The focus of this study was on testing such method, based on the approach of Knowledge Graphs. Knowledge Graphs are a structured way of representing information by connecting entities through relationships, often captured using SVO (Subject-Verb-Object) triplets. These triplets allow for a clearer understanding of how different concepts are related within the analysed data. Using Knowledge Graphs, the occurrences of disinformation in the messaging platform Telegram were investigated. Disinformation was sought by calculating different Graph Kernels between Knowledge Graphs constructed from collected Telegram messages and graphs made from already confirmed disinformation cases published in the EUvsDisinfo database. This method was applied to analyse more than 1 million messages from 30 Russian and Belarusian Telegram channels selected by experts, which, as the initial analysis showed, are also followed by Lithuanian citizens and frequently contain manifestations of disinformation. The disinformation cases were specifically selected only when they were related to the ongoing war between Russia and Ukraine. The results of the analysis showed that a certain amount of disinformation appeared in all the analysed channels, but most channels particularly emphasised disinformation related to biological and nuclear weapons, as well as the views of the residents of the occupied territories. When analysing the methods, it was found that the best way to form Graph Kernels for disinformation detection was the Shortest Path Kernel. This method, unlike others, allowed distinguishing the graphs most characterised by disinformation from the large number of graphs, which was the primary goal of this study. [ABSTRACT FROM AUTHOR]

The rapid increase of online content, which is often coupled with the ease with which people can share their opinions, has contributed to a rise in social issues such as cyberbullying, insults, and hate speech. To mitigate these issues, some online platforms have implemented measures like disabling anonymous comments or completely removing the option to comment on articles the users used to have. Additionally, certain platforms employ human moderators to identify and remove hate speech. However, due to a huge volume of online interactions, manually moderating content requires substantial human resources. Advances in artificial intelligence, particularly in natural language processing (NLP), offer promising results in hate speech identification. Automated hate speech detection systems can facilitate content moderation by effi- ciently processing and managing large volumes of data. In this study, we present a comparative evaluation of hate speech detection solutions for the Lithuanian language. We used several deep learning models for hate speech detection: Multilingual BERT, LitLat BERT, Electra, open Llama2 for the Lithuanian language, RWKV, BiLSTM, LSTM, CNN and ChatGPT. For the Electra model, we trained ourselves from scratch with Lithuanian texts that made more than 2.5 billion tokens. Multilingual BERT, LitLat BERT, Electra and RWKV were further fine-tuned to classify Lithuanian user-generated comments into three main classes: hate, offensive, and neutral speech. For comparison purposes, we also trained BiLSTM, LSTM and CNN models for the task. Open Llama2 for the Lithuanian language and ChatGPT were used without fine-tuning, and Open Llama2 for the Lithuanian language was then fine-tuned to get better results. To train or adapt the models to the hate speech detection task, we prepared an annotated dataset. It has had 27 357 user-generated comments (hate speech -- 4220, offensive -- 7821, neutral -- 15 316). All models were evaluated with accuracy, precision, recall, and F1-score metrics. Our future plans include augmentation of our annotated dataset with additional data sources and hate topics as well as experiments in model bias, robustness and output explainability. [ABSTRACT FROM AUTHOR]

Forest management in Lithuania is focused on sustainable development, balancing economic, environmental, and social objectives. Lithuanian forests, covering approximately one-third of the country's land area, are a critical resource for biodiversity, timber production, carbon sequestration, and recreation. To better understand how forests develop over time and how various factors influence their growth, it is important to identify tree growth functions. These functions are mathematical models that describe the relationship between forest growth and other variables such as age, environmental conditions, and management practices. Additionally, AI plays a crucial role in forest planning and management due to its ability to process large datasets, enhance decision-making, and improve sustainability practices. AI and machine learning (ML) are extensively used in forestry, as these methods enable the analysis of large datasets, including climate data, soil conditions, and historical forest management records, to optimise forest operations. For example, AI algorithms can help plan sustainable logging activities by predicting tree growth patterns and yield, while ML models assess the impact of different forest management practices on biodiversity and ecosystem health. AI-driven decision support systems can also assist in the realtime monitoring and management of forest resources, ensuring efficient and sustainable practices. This research aims to develop tree growth functions for Lithuanian forests and extend the GAYA stand simulator to new contexts, adapting it to Lithuanian conditions and reflecting the country's unique compositions of species and ecological conditions. We are integrating these growth functions into the GAYA framework to ensure accurate projections for Lithuanian forest ecosystems. Moreover, through a literature review, we have identified ways to improve forest planning using AI methods. Initial results show that estimating tree volume growth requires accounting for various forest parameters such as volume, height, age, diameter, and information about cutting activities. By applying ML models, forest planning can be further improved by integrating diverse datasets and evaluating multiple forest management scenarios. [ABSTRACT FROM AUTHOR]

Cancer patients often experience fluctuations in their health, which can be challenging to monitor continuously through traditional methods, such as patient self-reporting during clinic visits. With the growing prevalence of smartphones and their built-in sensors, new opportunities have emerged for real-time, passive monitoring of patient behaviour and health. These phone sensors -- tracking factors like physical activity, location, and phone usage -- can provide continuous data that may signal subtle changes in a patient's condition even before they become consciously aware of worsening symptoms. This research explores the use of phone sensor data to understand how real-time behavioural changes might be related to the onset of symptoms in cancer patients. By leveraging sensor data alongside patient surveys, the study investigates how patterns in daily activity, such as movement and phone usage, might signal an impending change in symptoms. The study included patients grouped by cancer type, gender, functional status (ECOG scale), and age. Loess regression and statistical analysis were applied to examine the dynamics of sensor data before and after symptom onset. Various variables describing patients' activity, such as distance from home, screen time ratio, and others, were evaluated over time using phone sensors. The study's results revealed that patients' activity levels, or time spent at home, begin to decline even before the patient reports the onset of symptoms, such as fatigue. The study found that tracking sensor readings can help predict worsening symptoms and facilitate early intervention, which is crucial to the quality of patient care. These findings highlight the importance of using phone sensors for real-time patient monitoring, enabling personalised care for cancer patients. [ABSTRACT FROM AUTHOR]

Fake news is becoming a recognised problem in society, creating large volumes of misinformation and raising questions about media integrity. The spread of misinformation has serious consequences, affecting public opinion, undermining trust in institutions, and sometimes leading to real-world harm. The sheer volume of information produced daily making manual verification of news impractical and time-consuming, leading in the need for automated tools that can assist with the issue. In this work, we present a proof of concept of a tool designed to detect disinformation in English-language media sources. At the core of our solution is the RoBERTa model, fine-tuned on a diverse set of articles from American (mostly for non-disinformation) and Russian (mostly for disinformation) English-language sources. This approach allows us to save time by avoiding the need to train the model from scratch. Additionally, RoBERTa's advanced capabilities, such as its ability to grasp the context and meaning of complex sentences and its bidirectional nature (analysing sentences from both the beginning to the end and in the opposite way), enable it to capture long-range dependencies between words. These features are valuable in identifying complex linguistic structures, such as hyperbole, unverified claims, biased language, and sarcasm, commonly found in news sources. Besides, we are using this approach to collect and analyse texts from Lithuanian media sources, focusing on various domains such as politics, economy, society, and business, to identify the prevalence of disinformation within these outlets. This allows us to gain insights into how misinformation is distributed across different sectors. To enhance the usability of our solution, we developed a Dash library-based web application that displays the model's evaluation results and delivers an intuitive interface for users to interact with the system. This application allows users to upload news articles or plain text, analyse them for potential misinformation, and view detailed, real-time feedback on the model's predictions. Additionally, the system allows for batch processing of multiple texts at once, providing scalability for larger datasets. The result of our work is a developed and tested version of a deep learning based disinformation detection system, capable of analysing disinformation in the selected national and international news and media sources and presenting the analysis results with an informative dashboard. [ABSTRACT FROM AUTHOR]

Arun Kumar Mishra wrote that every movement of goods from one point to the next must have the attached documents. According to Statista, logistics industry worldwide grows 0.5 trillion dollars each year, meaning more transportation is required the more documents needs to be processed. To efficiently manage huge volumes of documents and automate a decision-making process a classification system is required. This research focuses on logistics documents classification utilizing deep learning and machine learning algorithms. For this study, 50 GB of unlabeled data were presented, and the initial experiments were conducted using 5078 manually selected documents. Manually selected documents were assigned to 4 commonly used logistics document categories: CMRs, invoices, receipts, and others. The dataset was split into train and test sets, where 80% or 4058 of the documents were designated for training and 20% or 1014 of the documents for testing. Five main preprocessing steps were applied: convertion from PDF to JPG, resizing, deskewing, tint and noise removal. Two main methodologies were applied, application of neural networks and traditional machine learning classification techniques. Both approaches utilized pretrained backbone models on ImageNet. For neural networks we used Efficient-Net80, VGG16, MobileNet, ResNet50, DenseNet and InceptionV3. The neural network with the ResNet50 backbone outperformed other models achieving 0.9582 accuracy, 0.9593 precision, 0.9582 recall and 0.9585 F1 score. Rest models showed comparable results in performance evaluation: EfficientNet80 achieved 0.9467, VGG16 0.9176, MobileNet 0.9307, DenseNet 0.9387 and InceptionV3 0.9387 F1 scores. In addition, traditional machine learning classifiers, including Support Vector Machines (SVM), Random Forest, K-Nearest Neighbors (KNN), and XGBoost (XGB), were trained using features extracted from the ResNet50 backbone. The best-performing machine learning model was the Support Vector Classifier, achieving an accuracy of 0.9471, 0.9470 precision, 0.9471 recall and 0.9466 F1 score, while the XGBoost classifier, Random Forest, and KNearest Neighbors classifiers achieved F1 scores of 0.9440, 0.9455, and 0.9281, respectively. The research showed that the most promising solution for logistics document classification is the ResNet50 model and that it could be implemented in logistic environments to automate document separation. Future research will focus on dataset expansion utilizing pretrained ResNet50 model to label the remaining unused documents and further fine-tune models to enhance model F1 score, minimizing the need for human intervention in document classification. [ABSTRACT FROM AUTHOR]

The study presents a systematic review of 232 studies on various aspects of the use of artificial intelligence methods for identification of financial distress (such as bankruptcy or insolvency). We follow the guidelines of the PRISMA methodology for performing the systematic reviews. The study discusses bankruptcy-related financial datasets, data imbalance, feature dimensionality reduction in financial datasets, financial distress prediction, data pre-processing issues, non-financial indicators, frequently used machine-learning methods, performance evolution metrics, and other related issues of machine-learning-based workflows. The study findings revealed the necessity of data balancing, dimensionality reduction techniques in data preprocessing, and allow researchers to identify new research directions that have not been analyzed yet. [ABSTRACT FROM AUTHOR]

The goal of this study is to create a framework for route planning. The proposed approach considers the common features, i.e., picking up multiple freight according to the timewindows the pick-up and delivery locations have. However, a unique feature to the original Pickup-and-Delivery problem with time windows is introduced. Namely, freight can be redirected to depots for a fee, which lets drivers spend less time on the road and collect the redirected freights in one place. The genetic algorithm proves to be a viable approach as it produces reasonable results in a relatively short period of time. [ABSTRACT FROM AUTHOR]

There is an increasing need for training and testing data that can be used for the development of technologies and research. Due to data protection regulations, a lot of the realworld data -- especially the data from social media -- becomes unavailable to use. The problem can be solved by generating synthetic data that imitates the properties of real-world data. In this paper, we present Fabulator -- a social media generator that combines text and graph structure to be used for the generation of synthetic data and, in the future, for the simulation of various events on social media. [ABSTRACT FROM AUTHOR]

Pedestrian occurrences in images and videos must be accurately recognized in a number of applications that may improve the quality of human life. Radar can be used to identify pedestrians. When distinct portions of an object move in front of a radar, micro-Doppler signals are produced that may be utilized to identify the object. Using a deep-learning network and time–frequency analysis, we offer a method for classifying pedestrians and animals based on their micro-Doppler radar signature features. Based on these signatures, we employed a convolutional neural network (CNN) to recognize pedestrians and animals. The proposed approach was evaluated on the MAFAT Radar Challenge dataset. Encouraging results were obtained, with an AUC (Area Under Curve) value of 0.95 on the public test set and over 0.85 on the final (private) test set. The proposed DNN architecture, in contrast to more common shallow CNN architectures, is one of the first attempts to use such an approach in the domain of radar data. The use of the synthetic radar data, which greatly improved the final result, is the other novel aspect of our work. [ABSTRACT FROM AUTHOR]

Due to the fast pace of life and online communications and the prevalence of English and the QWERTY keyboard, people tend to forgo using diacritics, make typographical errors (typos) when typing in other languages. Restoring diacritics and correcting spelling is important for proper language use and the disambiguation of texts for both humans and downstream algorithms. However, both of these problems are typically addressed separately: the state-of-the-art diacritics restoration methods do not tolerate other typos, but classical spellcheckers also cannot deal adequately with all the diacritics missing.In this work, we tackle both problems at once by employing the newly-developed universal ByT5 byte-level seq2seq transformer model that requires no language-specific model structures. For a comparison, we perform diacritics restoration on benchmark datasets of 12 languages, with the addition of Lithuanian. The experimental investigation proves that our approach is able to achieve results (>98%) comparable to the previous state-of-the-art, despite being trained less and on fewer data. Our approach is also able to restore diacritics in words not seen during training with >76% accuracy. Our simultaneous diacritics restoration and typos correction approach reaches >94% alpha-word accuracy on the 13 languages. It has no direct competitors and strongly outperforms classical spell-checking or dictionary-based approaches. We also demonstrate all the accuracies to further improve with more training. Taken together, this shows the great real-world application potential of our suggested methods to more data, languages, and error classes. [ABSTRACT FROM AUTHOR]

This paper describes an experiment in testing 3 NER models (spaCy, Stanza and DeepPavlov) for Russian. The models were tested on WikiAnn Russian subset. Standard evaluation metrics (Precision, Recall and F-score) were complemented with 2 inter-annotator agreement measures (Fleiss' κ and Krippendorff's α). DeepPavlov performed better than the other 2 models in terms of all 3 standard performance measures. Stanza performed better than spaCy in terms of precision, while they shared the same F-measure score. Both Fleiss' κ and Krippendorff's α resulted in an only moderate agreement, showing, that our selected 3 NER models only moderately agree in terms of annotation of Russian named entities. [ABSTRACT FROM AUTHOR]

Current object detection models require tremendous number of annotated images to be able to get better accuracy. One issue related to the dataset creation task is that the annotation of large volumes of images is a very time-consuming and error-prone task. It is usual to come across multiple annotation errors like, for example, inconsistent annotations, misrepresentation of object class or missing an object altogether. Another issue related to the dataset creation is the volume of annotations that need to be modified in datasets. For example, if a car class needs to be split into smaller sub classes or a new object needs to be annotated, the whole dataset needs to be rechecked and fixed manually. In the case of virtual environments, it is sufficient to change the class of an object with annotations linked to an object that need to be fixed, so that the dataset can be re-generated at a higher speed as compared to manual annotations. To deal with the problems related to an array of image annotation task problems the current research promotes an approach to use virtual environments. These environments facilitate the generation of images' datasets by requiring solely the creation of a virtual scene from which datasets are generated for an object detection task. To create a virtual scene, one of the best game creation engines - "Unreal Engine" - is used. The following objects will be detected in the virtual scenes: vehicles (mostly military) and helicopters. The models of those objects are taken from openly accessible stores and from existing virtual simulation environment CARLA [1]. This simulated environment are used as a starting point for the building of the virtual scenes which had to be adapted for making datasets suitable for training object detection models. [ABSTRACT FROM AUTHOR]

This paper describes the construction and properties of the Lithuanian hate speech corpus. Initial data was collected from the Lithuanian news portal Delfi.lt. Then preprocessing was performed and user-generated comments under 13 selected news articles were annotated in 3 categories (Hate, Offensive, Neither). Currently, the Lithuanian hate speech corpus consists of 2372 user-generated comments (Hate - 445, Offensive - 288, Neither - 1639). All steps of preprocessing as well as statistical details of the corpus are discussed. This corpus was designed to contribute to publicly available ready-to-use Lithuanian lexical resources, therefore it will soon be available for public use. [ABSTRACT FROM AUTHOR]

This paper discusses research on Lithuanian texts of different styles for the development of the methodology for determining the informativity of Lithuanian texts. Research is based on the hypothesis that the informativity of texts can be measured by the weighted average of characteristics of individual levels, i.e. their lexical density and syntactic complexity. This research is an initial attempt to develop and, at the same time, test such methodology for Lithuanian language. The results of the research showed that the methodology developed and applied for determining the informativity of texts allows determining differences of the informativity of texts of different styles and is applicable to the Lithuanian language. [ABSTRACT FROM AUTHOR]

Visualization systems are becoming increasingly popular for network data analysis. There had been many approaches to visualize network traffic and detect anomalous events. However, most of the systems faced various difficulties, including high volumes of data, insufficient number of method dimensions and uninformative results achieved with visualizations. In this paper we present our approach to network data visualization. The system works with four local addresses and provides detailed information about their traffic. Server load graphs and chord diagrams were used to obtain information about local addresses and combination of these methods was used to create a framework of network flow monitoring. Our system analysis showed that it is possible to identify multiple valid or invalid logins, remote large data transmissions, and sudden changes in server load. [ABSTRACT FROM AUTHOR]

This research describes the problem of classification method selection for credit scoring. Credit risk is one of main risks of financial institutions. That's why researchers and analysts are constantly looking for better credit scoring model creation. Nowadays, a number of different features, such as information about the clients: his habits, previous credits, bank accounts' information, insurance and other, can be included in credit scoring models. In recent years, deep learning become one of the most popular machine learning methods due to its performance. One of deep learning methods is convolution neural network (ConvNet), which learns all aspects directly from the data, by creating network layers, which in abstract level reveals the main features of the category. This method is suitable to accommodate large number of features and have good accuracy results, what's why such companies as: Google, Facebook, Microsoft, IBM is using it for different classification tasks. Three real-world data sets from UCI repository are obtained in the experiments for credit scoring problems. Different ConvNet architectures were created random for each data set, based on the logic of the wrapper method (to optimize the accuracy). These results are compered in three ways: with each other; with conventional machine learning methods; with the works of other authors. The experimental outcomes reveal the further development of the ConvNet is expedient in a larger number of features and data sets, either in the combinations of different voting of classifications algorithms (including the ConvNet method). [ABSTRACT FROM AUTHOR]

We discuss an experiment on automatic identification of bi-gram multiword expressions (MWE) in parallel Latvian and Lithuanian corpora. Raw corpora, lexical association measures (LAMs) and supervised machine learning (ML) are used due to the scarceness and quality of lexical resources (e.g., POS-tagger, parser) and tools. Combining LAMs with ML works well for other languages, our experiments show that it perform well for Lithuanian and Latvian as well. We analyse and discuss frequency thresholds in terms of potential MWE and LAMs values. Finally, combining LAMs with ML we have achieved 98,8% precision and 57,5% recall for Latvian and 96,9% precision and 61,8% recall for Lithuanian. [ABSTRACT FROM AUTHOR]

The changes and evolution of the electricity distribution has provided new possibilities to the electricity providers for developing a better marketing and trading strategies. A key aspect for designing specific tariff structures is the identification of customers groups exhibiting similar consumption patterns. This paper presents a new methodology for the classification of electricity customers on the basis of their electrical behaviour. Approach is based on the periodicity analysis and well known clustering technique - k-means. The paper presents the classification results obtained on a set of 3753 industrial users, whose consumption has been monitored for 3 years. [ABSTRACT FROM AUTHOR]

In this paper we report on the development of the prototype of Internet media monitoring tool for Lithuanian government. Two design specificities are emphasized. First, the tool must to a maximum possible extent utilize the open access and open source tools and resources available. Second, this university-lead open mode of the tool development must be conducted in close collaboration with governmental agencies operating under confidentiality seal. Having successfully developed the media monitoring prototype, two key findings are reported: 1) the conceptual model of the Internet media monitoring tool based on open access Internet infrastructure resources; and 2) the system design method for balancing public and confidential requirements towards the system. [ABSTRACT FROM AUTHOR]

Using a ResNet-18 Network to Detect Features of Alzheimer's Disease on Functional Magnetic Resonance Imaging: A Failed Replication. The ADNI MR data set includes a wide range of scanner platforms; however, there has been a broad gap between older MRI systems and the state-of-the-art systems within each vendor's product line. In fact, it is in line with the state-of-the-art studies, which achieved a similar high performance in the ADNI dataset by using 2D CNN, ResNet-18 [[7]] and custom CNN [[8]], as well as in other datasets such as OASIS [[9]]. [Extracted from the article]

We develop a process algebraic framework PAFSV for the formal specification and analysis of IEEE 1800™ SystemVerilog designs. The formal semantics of PAFSV is defined by means of deduction rules that associate a time transition system with a PAFSV process. A set of properties of PAFSV is presented for a notion of bisimilarity. PAFSV may be regarded as the formal language of a significant subset of IEEE 1800™ System Verilog. To show that PAFSV is useful for the formal specification and analysis of IEEE 1800™ System Verilog designs, we illustrate the use of PAFSV with a multiplexer, a synchronous reset D flip-flop and an arbiter. [ABSTRACT FROM AUTHOR]

Copyright of Darbai ir Dienos is the property of Vytautas Magnus University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The goal of the radiation therapy is to give as much dose as possible to the target volume of tissue and avoid giving any dose to a healthy tissue. Advances of the digital control allow performing accurate plans and treatments. Unfortunately, motion compensation during the treatment remains a considerable problem. Currently, combination of the different techniques, such as gating (restricting movement of patient) and periodic emission are used to avoid damaging healthy tissue We are interested in systems that completely compensate respiratory movement (up to certain limit) and start by investigating adequacy of the existing hardware and software platform. We model a radiation therapy system consisting of a HexaPOD couch with 6-degrees movement, a tracking camera, a marker (markers) and a controller. Formal un-timed and timed models were defined, analyzed and found to be insufficient to completely determine adequacy of the system to compensate respiratory motion. We define one-dimensional hybrid model of the system using Open Modelica tool and investigate the model with simple tumor movement trajectories, and based on the results we sketch further development directions. [ABSTRACT FROM AUTHOR]

The goal of radiation therapy is to give as much dose as possible to the target volume of tissue and avoid giving any dose to a healthy tissue. Advances of the digital control allow performing accurate plans and treatments. Unfortunately, motion compensation during the treatment remains a considerable problem. Currently, a combination of the different techniques, such as gating (restricting movement of patient) and periodic emission are used to avoid damaging healthy tissue. This paper focuses on systems that completely compensate respiratory movement (up to certain limit) and start by investigating adequacy of the existing hardware and software platform. In this paper a radiation therapy system consisting of a HexaPOD couch with 6-degrees movement, a tracking camera, a marker (markers) and a controller is modeled. A formal un-timed model was evaluated and found to be insufficient to completely determine adequacy of the system to compensate respiratory motion. Therefore, un-timed model was extended to include time and investigated. It provides more information than un-timed model, but does not answer all interesting question. Therefore, based on the results further research directions are sketched. [ABSTRACT FROM AUTHOR]